# A tibble: 6 × 6,701
Diet Source Donor CollectionMet Sex OTU0 OTU1 OTU2 OTU3
<dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
1 0 0 0 0 0 1.56e-11 4.72e-11 1.23e-11 4.52e-11
2 0 1 0 0 0 2.36e-11 9.53e-11 3.33e-11 2.67e-11
3 0 2 0 1 0 6.77e-11 3.68e-11 8.02e-11 5.49e-11
4 0 2 0 0 0 5.52e-11 9.89e-11 4.58e-11 3.54e-11
5 0 3 0 0 0 5.24e-11 6.34e-11 2.35e-11 7.47e-11
6 0 4 0 1 0 7.67e-11 7.22e-11 5.41e-11 1.20e-11
# ℹ 6,692 more variables: OTU4 <dbl>, OTU5 <dbl>, OTU6 <dbl>, OTU7 <dbl>,
# OTU8 <dbl>, OTU9 <dbl>, OTU10 <dbl>, OTU11 <dbl>, OTU12 <dbl>, OTU13 <dbl>,
# OTU14 <dbl>, OTU15 <dbl>, OTU16 <dbl>, OTU17 <dbl>, OTU18 <dbl>,
# OTU19 <dbl>, OTU20 <dbl>, OTU21 <dbl>, OTU22 <dbl>, OTU23 <dbl>,
# OTU24 <dbl>, OTU25 <dbl>, OTU26 <dbl>, OTU27 <dbl>, OTU28 <dbl>,
# OTU29 <dbl>, OTU30 <dbl>, OTU31 <dbl>, OTU32 <dbl>, OTU33 <dbl>,
# OTU34 <dbl>, OTU35 <dbl>, OTU36 <dbl>, OTU37 <dbl>, OTU38 <dbl>, …Impact of Dietary Shifts on Gut Microbiome Dynamics
Multivariate Insights Using R
R for Bio Data Analysis
2024-12-03
Objective and Main Research Questions
Metagenomics study focusing on an animal model of the human gut ecosystem obtained by transplanting fresh human fecal microbial communities into germ-free C57BL/6J mice.
Measuring the effects of diet (Western or Low-Fat Plant Polysaccharide-rich), temporal and spatial composition of the microbiota, colonisation history…
Our aim:
To study the relationship between the composition of the gut microbiota and factors such as diet and colonisation history.
Main Research Questions:
Modelling of the Firmicutes-Bacteroidetes ratio
Deciphering key factors shaping ecosystem composition through PCA and clustering analysis
Evalauting the effect of diet in the microbial biodiversity
General Workflow
Microbiota composition in terms of phyla in different:
sources and diet types
![]()
diet and donor combination
![]()
Principal Component Analysis on Phylum-Level Aggregated Microbiome Data
# Aggregate relative abundances by phylum
aggregated_data <- clean_df_augm |>
filter(Donor == "Fresh") |> #we select the first generation of humanised mice (we don't select the western and lfpp diet as these are the only diets these mice follow)
group_by(SampleID, Phylum, Diet) |>
summarize(rel_abundance = sum(rel_abundance), .groups = "drop")
# Pivot wider and one-hot coding of diet variable to prepare for PCA (SampleID by Phylum)
aggregated_wide <- aggregated_data |>
pivot_wider(names_from = Phylum, values_from = rel_abundance) |>
mutate(Diet = case_when(Diet == "LFPP" ~ 0, Diet == "Western" ~ 1)) #pca uses numerical values so we modify the diet column
# Check of the aggregated data
head(aggregated_wide)
Principal Component Analysis on Phylum-Level Aggregated Microbiome Data
Analysis of Microbiome Clusters by Donor Groups Using Hierarchical Clustering
# Read the metadata in wide format
filtered_metadata_wider <- read_tsv("../data/02_metadata_wide_filtered_label.tsv")
# Select OTU columns
otu_data <- filtered_metadata_wider |>
select(starts_with("OTU"))
# Scale the OTU data
otu_data_scaled <- otu_data |>
scale()
# Convert scaled matrix back to tibble for tidyverse compatibility
otu_data_scaled <- as_tibble(otu_data_scaled)
# Add relevant metadata (e.g., Donor)
otu_data_with_metadata <- otu_data_scaled |>
mutate(Donor = filtered_metadata_wider |> pull(Donor))
# Compute Euclidean distance matrix
dist_matrix <- otu_data_scaled |>
dist()
# Perform hierarchical clustering
hclust_result <- hclust(dist_matrix, method = "ward.D2")
# Cut dendrogram into 3 clusters
cluster_labels <- cutree(hclust_result, k = 3) |>
as_tibble() |>
rename(Cluster = value)
# Attach cluster labels to metadata
clustered_metadata <- filtered_metadata_wider |>
mutate(Cluster = cluster_labels |> pull(Cluster))